Training in progress, step 10000
Browse files- .gitignore +1 -0
- config.json +33 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/gpfs/home/ikuzmin/hier-bert-pytorch/data/hier-model",
|
3 |
+
"architectures": [
|
4 |
+
"HierBertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "configuration_hier.HierBertConfig",
|
9 |
+
"AutoModel": "modelling_hier.HierBertModel",
|
10 |
+
"AutoModelForMaskedLM": "modelling_hier.HierBertForMaskedLM",
|
11 |
+
"AutoModelForSequenceClassification": "modelling_hier.HierBertForSequenceClassification"
|
12 |
+
},
|
13 |
+
"classifier_dropout": null,
|
14 |
+
"hidden_act": "gelu",
|
15 |
+
"hidden_dropout_prob": 0.1,
|
16 |
+
"hidden_size": 512,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 2048,
|
19 |
+
"layer_norm_eps": 1e-06,
|
20 |
+
"max_position_embeddings": 512,
|
21 |
+
"model_type": "hierarchical-bert",
|
22 |
+
"norm_first": true,
|
23 |
+
"num_attention_heads": 8,
|
24 |
+
"num_hidden_layers": 6,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"position_embedding_type": "absolute",
|
27 |
+
"sep_token_id": 3,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.31.0",
|
30 |
+
"type_vocab_size": 2,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 32000
|
33 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95137e110b61e4e482de18d6b3c5da7c3172fe18108277525825669caf04b615
|
3 |
+
size 143455588
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a971dccbc187e9e622d3b1318b56a1fb401050edee0c98c2c6ff0ba027c6a686
|
3 |
+
size 802659
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "[CLS]",
|
5 |
+
"do_lower_case": false,
|
6 |
+
"eos_token": "[SEP]",
|
7 |
+
"mask_token": "[MASK]",
|
8 |
+
"max_len": 512,
|
9 |
+
"model_max_length": 512,
|
10 |
+
"pad_token": "[PAD]",
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"sp_model_kwargs": {},
|
13 |
+
"split_by_punct": false,
|
14 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f59d599c000a9dae6029191418497a813544fa3e5341b3436c6c16ed3c299be
|
3 |
+
size 4091
|